aboutsummaryrefslogtreecommitdiffstats
path: root/linguistics-components/src/main/resources/configdefinitions/language.wordpiece.word-piece.def
blob: 1d70255d97e087fbbe96de27cea42eb445928331 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
# Copyright Vespa.ai. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root.

# Configures com.yahoo.language.wordpiece.WordPieceEmbedder

namespace=language.wordpiece

# The prefix to prepend to subword tokens
subwordPrefix string default="##"

# The language a model is for, one of the language tags in com.yahoo.language.Language.
# Use "unknown" for a model to be used for any language (i.e by default).
model[].language string
# The path to the model relative to the application package root
model[].path path